Clarify for AI agents

Clarify is a CRM that lets an agent query and update records, build task lists, and analyze pipelines across companies, people, and deals. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

CRMOAuth 2.0 (MCP)MCP + RESTclarify.ai
AUDIT LOG · CLARIFYPOLICY: acme-support
09:41:09 · claude · u_8f2write
clarify.add_comment
Add-comment✓ approved · approved by user
EVERY CLARIFY CALL, ON THE RECORD
01 · USE CASES

What agents do in Clarify.

01

Add a comment to a deal

Add a comment to a deal record to log context from a recent call.

02

Check a pipeline's open deals

Check which deals are open in a pipeline before prioritizing follow-up for the week.

03

Create a task for a contact

Create a follow-up task tied to a specific contact so nothing falls through.

02 · ACTIONS

1 Clarify actions, graded by risk.

Every Clarify action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

0

Look things up. Allowed by default.

  • No read actions.

write

1

Create and change things. Allow, or ask the user first.

  • clarify.add_comment
    Add-comment

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Clarify in three steps.

  1. 01Your users connect ClarifyThey sign in to Clarify on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, and writes like “add-comment” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Clarify through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('clarify', {
  read: 'allow',
  write: 'ask',        // add_comment
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Clarify connects.

Clarify runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Clarify through the same endpoint, policies and audit log as every other app.

The same Clarify connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
OAuth 2.0 (MCP)
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Clarify from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Clarify and Arc0, answered.

Q01

Can I use Clarify with Claude, ChatGPT or Cursor?

Yes. Connect Clarify to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Clarify actions you allow.

Q02

How do users connect Clarify?

Clarify runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Clarify through the same endpoint, policies and audit log as every other app.

Q03

Which Clarify actions can my agent take?

1 in total: 0 read, 1 write and 0 destructive, such as “add-comment”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Clarify?

Yes. Allow read actions and deny writes in the Clarify policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Clarify too?

Yes. The same Clarify connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Clarify into your agent.

Your users connect Clarify once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan